Abstract
With the rise of 5G network and the rapid growth of user equipment, there exists a gap between the stringent requirements of emerging applications and the actual functionality of the Internet. In particular, transmitting data over long network links imposes high costs, which can be addressed by the edge caching (EC) method. EC caches the content at the edge server to avoid the extraordinary cost of backhaul link communication. However, in existing EC efforts, it is common to assume either known content popularity or a two-phase caching that is predicted content popularity prior to the caching action, the former being less feasible and the latter increasing the cost of deployment to the real world. A caching strategy is proposed in this paper to cope with this problem that can be feasible end-to-end deployed and has a lower caching cost. Specifically, we first investigate the system cost, including network communication cost, cache over storage cost, and cache replacement cost. And we model the EC problem as a Markov Decision Process (MDP). Then, the Double Deep Recurrent Q Network (DDRQN) algorithm is studied to solve the EC-based MDP problem. Finally, compared with other intelligent caching strategies, the proposed caching strategy can improve the system reward by up to 24% and the cache hit rate by up to 22% under certain conditions.
Similar content being viewed by others
References
Cisco (2020) Cisco annual internet report (2018–2023) white paper. [Online]. Available: https://www.cisco.com/c/en/us/solutions/collateral/executive-perspectives/annual-internet-report/white-paper-c11-741490.html
Pham Q-V, Fang F, Ha VN, Piran MJ, Le M, Le LB, Hwang W-J, Ding Z (2020) A survey of multi-access edge computing in 5g and beyond: Fundamentals, technology integration, and state-of-the-art. IEEE Access 8:116974–117017
Velte T, Velte A, Elsenpeter R (2009) Cloud computing, a practical approach. McGraw-Hill, Inc.
Zhou Z, Chen X, Li E, Zeng L, Luo K, Zhang J (2019) Edge intelligence: Paving the last mile of artificial intelligence with edge computing. Proc IEEE 107(8):1738–1762
Xu Y, Gu B, Hu RQ, Li D, Zhang H (2021) Joint computation offloading and radio resource allocation in mec-based wireless-powered backscatter communication networks. IEEE Trans Veh Technol 70(6):6200–6205
Zhuang W, Ye Q, Lyu F, Cheng N, Ren J (2019) Sdn/nfv-empowered future iov with enhanced communication, computing, and caching. Proc IEEE 108(2):274–291
Xia X, Chen F, He Q, Grundy J, Abdelrazek M, Jin H (2020) Online collaborative data caching in edge computing. IEEE Trans Parallel Distrib Syst 32(2):281–294
Nour B, Khelifi H, Moungla H, Hussain R, Guizani N (2020) A distributed cache placement scheme for large-scale information-centric networking. IEEE Network
Ale L, Zhang N, Wu H, Chen D, Han T (2019) Online proactive caching in mobile edge computing using bidirectional deep recurrent neural network. IEEE Internet Things J 6(3):5520–5530
Wu Z, Lu Z, Zhang W, Wu J, Huang S, Hung PC (2018) A data-driven approach of performance evaluation for cache server groups in content delivery network. J Parallel Distrib Comput 119:162–171
Zeng Y, Xie J, Jiang H, Huang G, Yi S, Xiong N, Li J (2019) Smart caching based on user behavior for mobile edge computing. Inf Sci 503:444–468
Rathore S, Ryu JH, Sharma PK, Park JH (2019) Deepcachnet: a proactive caching framework based on deep learning in cellular networks. IEEE Network 33(3):130–138
Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529–533
Zhong C, Gursoy MC, Velipasalar S (2018) A deep reinforcement learning-based framework for content caching. In: 2018 52nd Annual Conference on Information Sciences and Systems (CISS). IEEE, pp 1–6
He X, Wang K, Xu W (2019) Qoe-driven content-centric caching with deep reinforcement learning in edge-enabled iot. IEEE Comput Intell Mag 14(4):12–20
Qiao G, Leng S, Maharjan S, Zhang Y, Ansari N (2019) Deep reinforcement learning for cooperative content caching in vehicular edge computing and networks. IEEE Internet Things J 7(1):247–257
Hou L, Lei L, Zheng K, Wang X (2018) A q-learning-based proactive caching strategy for non-safety related services in vehicular networks. IEEE Internet Things J 6(3):4512–4520
Li S, Li B, Zhao W (2020) Joint optimization of caching and computation in multi-server noma-mec system via reinforcement learning. IEEE Access 8:112762–112771
Hausknecht M, Stone P (2015) Deep recurrent q-learning for partially observable mdps. arXiv preprint: arXiv:1507.06527
Liu Y, He Q, Zheng D, Xia X, Chen F, Zhang B (2020) Data caching optimization in the edge computing environment. IEEE Trans Serv Comput 1–8
Hu Z, Zheng Z, Wang T, Song L, Li X (2016) Game theoretic approaches for wireless proactive caching. IEEE Commun Mag 54(8):37–43
Yu G, Wu J (2020) Content caching based on mobility prediction and joint user prefetch in mobile edge networks. Peer-to-Peer Netw Appl 13(5):1839–1852
Saputra YM, Hoang DT, Nguyen DN, Dutkiewicz E, Niyato D, Kim DI (2019) Distributed deep learning at the edge: a novel proactive and cooperative caching framework for mobile edge networks. IEEE Wireless Commun Lett 8(4):1220–1223
Liang J, Zhu D, Liu H, Ping H, Li T, Zhang H, Geng L, Liu Y (2020) Multi-head attention based popularity prediction caching in social content-centric networking with mobile edge computing. IEEE Commun Lett 25(2):508–512
Bernardini C, Silverston T, Festor O (2014) Sonetor: a social network traffic generator. In: 2014 IEEE International Conference on Communications (ICC). IEEE, pp 3734–3739
Tang B, Kang L (2021) Eicache: a learning-based intelligent caching strategy in mobile edge computing. Peer-to-Peer Netw Appl 1–16
Zhu H, Cao Y, Wang W, Jiang T, Jin S (2018) Deep reinforcement learning for mobile edge caching: Review, new features, and open issues. IEEE Network 32(6):50–57
Wang X, Han Y, Wang C, Zhao Q, Chen X, Chen M (2019) In-edge AI: Intelligentizing mobile edge computing, caching and communication by federated learning. IEEE Network 33(5):156–165
Zhang N, Zheng K, Tao M (2018) Using grouped linear prediction and accelerated reinforcement learning for online content caching. In: 2018 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE, pp 1–6
Tang J, Tang H, Zhang X, Cumanan K, Chen G, Wong K-K, Chambers JA (2019) Energy minimization in d2d-assisted cache-enabled internet of things: a deep reinforcement learning approach. IEEE Trans Industr Inf 16(8):5412–5423
Ye Z, Zhang D, Wu Z-G, Yan H (2021) A3c-based intelligent event-triggering control of networked nonlinear unmanned marine vehicles subject to hybrid attacks. IEEE Trans Intell Transport Syst
Zhao Y, Li R, Wang C, Wang X, Leung VC (2021) Neighboring-aware caching in heterogeneous edge networks by actor-attention-critic learning. In: ICC 2021-IEEE International Conference on Communications. IEEE, pp 1–6
Xu Y, Xie H, Li D, Hu RQ (2022) Energy-efficient beamforming for heterogeneous industrial iot networks with phase and distortion noises. IEEE Trans Ind Inform
Ghemawat S, Gobioff H, Leung S-T (2003) The google file system. In: Proceedings of the Nineteenth ACM Symposium on Operating Systems Principles, pp 29–43
Watkins CJ, Dayan P (1992) Q-learning. Mach Learn 8(3–4):279–292
Van Hasselt H, Guez A, Silver D (2015) Deep reinforcement learning with double q-learning. arXiv preprint: arXiv:1509.06461
Zhang D, Ye Z, Chen P, Wang Q-G (2020) Intelligent event-based output feedback control with q-learning for unmanned marine vehicle systems. Control Eng Pract 105:104616
Zhang D, Ye Z, Feng G, Li H (2021) Intelligent event-based fuzzy dynamic positioning control of nonlinear unmanned marine vehicles under dos attack. IEEE Trans Cybern
Funding
This work is supported by National Science Foundation of China under Grant 61703127, Key R&D Program of Zhejiang Province 2021C01114, and the Graduate Scientific Research Foundation of Hangzhou Dianzi University CXJJ2020087.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
All authors in this work declared that they have no conflicts of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Xu, H., Sun, Y., Gao, J. et al. Intelligent edge content caching: A deep recurrent reinforcement learning method. Peer-to-Peer Netw. Appl. 15, 2619–2632 (2022). https://doi.org/10.1007/s12083-022-01369-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12083-022-01369-6